Agents and New Risk

Agentic AI's fresh attack surface.

  • 37 Tracked terms
  • Last 30 days Feed window
Search within this topic Ask AI about this topic All topics

Where the coverage comes from

The 50 sources publishing most on Agents and New Risk over the last 30 days, out of 2,337 articles in the feed. Click a source for its articles on this topic and its profile.

  1. 1 @Thepracticaldev dev.to 199 articles 1+ hour ago 98%
  2. 2 Medium medium.com 72 articles 1+ hour ago 83%
  3. 3 Pr Newswire prnewswire.com 28 articles 2+ day ago 89%
  4. 4 Cybersecuritynews cybersecuritynews.com 27 articles 2+ day ago 0%
  5. 5 Siliconangle siliconangle.com 27 articles 1+ day ago 93%
  6. 6 @Businessline thehindubusinessline.com 27 articles 2+ week ago 100%
  7. 7 @Forbes forbes.com 26 articles 2+ day ago 100%
  8. 8 Forkast forkast.news 25 articles 4+ hour ago 100%
  9. 9 @Hackernoon hackernoon.com 25 articles 3+ day ago 96%
  10. 10 Crypto Briefing cryptobriefing.com 24 articles 3+ day ago 96%
  11. 11 crn.com 22 articles 2+ day ago 91%
  12. 12 Yahoo Finance finance.yahoo.com 22 articles 2+ day ago 91%

In the feed right now

Tags
People
Places
Organizations

What this topic collects on

An article joins this feed when it matches these terms. Each one is also a search of its own.

Latest in Agents and New Risk

DEV Community
dev.to > cole_halton_42f71d71b809b > the-rubygems-agent-attack-is-a-coding-agent-benchmark-nobody-writes-2c6e

The RubyGems agent attack is a coding-agent benchmark nobody writes

1+ hour, 50+ min ago   (345+ words) This week the reports landed: an OpenAI agent swarm had been quietly uploading packages to RubyGems since early May. Over 2,000 packages on May 11-12 alone, naming themselves with "oai" prefixes, eventually forcing the registry to disable new-user signups for four days....

DEV Community
dev.to > tinycoder-studio > i-found-an-undocumented-mcp-server-on-opensea-and-it-leaked-usernames-for-any-wallet-5935

I Found an Undocumented MCP Server on OpenSea — and It Leaked Usernames for Any Wallet

2+ hour, 13+ min ago   (492+ words) TL;DR: OpenSea runs an undocumented MCP server at mcp.opensea.io/mcp. One of its tools hands out API keys to anyone who asks, and another lets you resolve any Ethereum address with an OpenSea profile to its owner's…...

DEV Community
dev.to > balbaks > i-ran-my-scanner-against-5-real-cves-it-missed-4-then-i-reverted-my-own-fix-4dhk

I ran my scanner against 5 real CVEs. It missed 4. Then I reverted my own fix.

4+ hour, 12+ min ago   (657+ words) Why this post is different from the last one The last write-up in this series announced four tools. This one is about what happened when I stopped writing tests for my own tools and started checking one of them against…...

Forkast
forkast.news > the-hidden-cost-of-securing-your-smart-homes-ai-agent-chain

The Hidden Cost of Securing Your Smart Home’s AI Agent Chain

4+ hour, 43+ min ago   (130+ words) Multi-agent smart home systems cost 5-10x more to build than single-agent tools. The protocol powering them executes OS commands by design. And regulators haven't caught up. The era of the “free” smart home was always a myth. Sonos isn’t charging you…...

Forkast
forkast.news > intent-based-access-control-runtime-authority-as-infrastructure

Intent-Based Access Control: Runtime Authority as Infrastructure

5+ hour, 1+ min ago   (272+ words) Akeyless's GA release formalizes intent-based access control as a distinct infrastructure layer — the first production-ready product to bridge the gap between governance specification and runtime enforcement for AI agents. On September 9, 2026, Akeyless moved its Agentic Runtime Authority into general availability....

Medium
medium.com > @ramshazafar2 > the-ai-agent-security-problem-why-your-cloud-needs-an-identity-strategy-for-the-ai-workforce-f5f65f9f3078

The AI Agent Security Problem: Why Your Cloud Needs an Identity Strategy for the AI Workforce

1+ hour, 36+ min ago   (1269+ words) AI agents are moving beyond experiments. Businesses are increasingly using them to automate tasks …...

EconoTimes
econotimes.com > OpenAI-Agents-Linked-to-RubyGems-Cyberattack-1751905

OpenAI Agents Linked to RubyGems Cyberattack

21+ hour, 59+ min ago   (508+ words) Kioxia Rules Out SK Hynix Manufacturing Partnership U.S. Accuses Chinese AI Firms of Extracting Model Capabilities Can Europe shake its Russia links for good? Nvidia Plans 2GW Australia AI Data Center Expansion by 2027 Huawei, Chinese AI Chipmakers Raise Prices as HBM Shortage…...

Medium
medium.com > @nguyenan04/10/2004 > the-dead-web-swarm-how-openais-agents-colonized-abandoned-internet-servers-404e3cfb209b

The Dead Web Swarm: How OpenAI’s Agents Colonized Abandoned Internet Servers

1+ hour, 48+ min ago   (500+ words) By An Nguyen — September 12, 2026 Topics: Instrumental-Convergence, Side-Channel-Communication …...

Engadget
engadget.com > 2256741 > openai-agents-hacked-rubygems

OpenAI agents hacked a software service before the Hugging Face incident

6+ hour, 14+ min ago   (492+ words) The agents OpenAI was testing attacked a software service called RubyGems in May, months before the attacks on Hugging Face. OpenAI agents hacked a software service before the Hugging Face incident A group of researchers discovered another previously undisclosed cyberattack…...

DEV Community
dev.to > efek > metasploit-payload-generation-room-writeup-9nh

TryHackMe Metasploit: Payload Generation Room Writeup

7+ hour ago   (41+ words) TASK 2 What flag sets the output format in msfvenom? Answer: -f What flag specifies the payload... Tagged with cybersecurity, tryhackme, metasploit, lab....